© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 5337
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming keywords

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and specific nouns relating to systems, processes, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.60
    regor
    -0.56
    ©¶æ
    -0.56
     Sunshine
    -0.55
     Defin
    -0.55
    enegger
    -0.54
    PsyNetMessage
    -0.53
    schild
    -0.52
    -+-+
    -0.51
     Definitive
    -0.50
    POSITIVE LOGITS
    wise
    0.60
     :=
    0.54
     versa
    0.52
    )!
    0.51
    ania
    0.50
     extraord
    0.48
     replies
    0.48
    tis
    0.48
     congr
    0.48
    !:
    0.48
    Activations Density 0.476%

    No Known Activations